Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a s...Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.展开更多
A model-based optimal dispatch framework was proposed to optimize operation of residential flexible loads considering their real-life operating characteristics,energy-related occupant behavior,and the benefits of diff...A model-based optimal dispatch framework was proposed to optimize operation of residential flexible loads considering their real-life operating characteristics,energy-related occupant behavior,and the benefits of different stakeholders.A pilot test was conducted for a typical household.According to the monitored appliance-level data,operating characteristics of flexible loads were identified and the models of these flexible loads were developed using multiple linear regression and K-means clustering methods.Moreover,a data-mining approach was developed to extract the occupant energy usage behavior of various flexible loads from the monitored data.Occupant behavior of appliance usage,such as daily turn-on times,turn-on moment,duration of each operation,preference of temperature setting,and flexibility window,were determined by the developed data-mining approach.Based on the established flexible load models and the identified occupant energy usage behavior,a many-objective nonlinear optimal dispatch model was developed aiming at minimizing daily electricity costs,occupants’dissatisfaction,CO_(2) emissions,and the average ramping index of household power profiles.The model was solved with the assistance of the NSGA-III and TOPSIS methods.Results indicate that the proposed framework can effectively optimize the operation of household flexible loads.Compared with the benchmark,the daily electricity costs,CO_(2) emissions,and average ramping index of household power profiles of the optimal plan were reduced by 7.3%,6.5%,and 14.4%,respectively,under the TOU tariff,while those were decreased by 9.5%,8.8%,and 23.8%,respectively,under the dynamic price tariff.The outputs of this work can offer guidance for the day-ahead optimal scheduling of household flexible loads in practice.展开更多
基金the Shanghai Rising-Star Program(No.22QA1403900)the National Natural Science Foundation of China(No.71804106)the Noncarbon Energy Conversion and Utilization Institute under the Shanghai Class IV Peak Disciplinary Development Program.
文摘Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.
基金This work was supported by the National Natural Science Foundation of China(52278104)the Science and Technology Innovation Program of Hunan Province(2017XK2015).
文摘A model-based optimal dispatch framework was proposed to optimize operation of residential flexible loads considering their real-life operating characteristics,energy-related occupant behavior,and the benefits of different stakeholders.A pilot test was conducted for a typical household.According to the monitored appliance-level data,operating characteristics of flexible loads were identified and the models of these flexible loads were developed using multiple linear regression and K-means clustering methods.Moreover,a data-mining approach was developed to extract the occupant energy usage behavior of various flexible loads from the monitored data.Occupant behavior of appliance usage,such as daily turn-on times,turn-on moment,duration of each operation,preference of temperature setting,and flexibility window,were determined by the developed data-mining approach.Based on the established flexible load models and the identified occupant energy usage behavior,a many-objective nonlinear optimal dispatch model was developed aiming at minimizing daily electricity costs,occupants’dissatisfaction,CO_(2) emissions,and the average ramping index of household power profiles.The model was solved with the assistance of the NSGA-III and TOPSIS methods.Results indicate that the proposed framework can effectively optimize the operation of household flexible loads.Compared with the benchmark,the daily electricity costs,CO_(2) emissions,and average ramping index of household power profiles of the optimal plan were reduced by 7.3%,6.5%,and 14.4%,respectively,under the TOU tariff,while those were decreased by 9.5%,8.8%,and 23.8%,respectively,under the dynamic price tariff.The outputs of this work can offer guidance for the day-ahead optimal scheduling of household flexible loads in practice.
